ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation
This addresses the problem of biased and inefficient automatic evaluation metrics for natural language generation tasks like machine translation and summarization, offering an incremental improvement over existing LLM-based methods.
The paper tackles the challenge of evaluating generated text by introducing ContrastScore, a contrastive evaluation metric that achieves stronger correlation with human judgments than baselines, with Qwen 3B and 0.5B versions outperforming Qwen 7B despite having fewer parameters.
Evaluating the quality of generated text automatically remains a significant challenge. Conventional reference-based metrics have been shown to exhibit relatively weak correlation with human evaluations. Recent research advocates the use of large language models (LLMs) as source-based metrics for natural language generation (NLG) assessment. While promising, LLM-based metrics, particularly those using smaller models, still fall short in aligning with human judgments. In this work, we introduce ContrastScore, a contrastive evaluation metric designed to enable higher-quality, less biased, and more efficient assessment of generated text. We evaluate ContrastScore on two NLG tasks: machine translation and summarization. Experimental results show that ContrastScore consistently achieves stronger correlation with human judgments than both single-model and ensemble-based baselines. Notably, ContrastScore based on Qwen 3B and 0.5B even outperforms Qwen 7B, despite having only half as many parameters, demonstrating its efficiency. Furthermore, it effectively mitigates common evaluation biases such as length and likelihood preferences, resulting in more robust automatic evaluation.